A path planning method, device, medium, and program product based on BeiDou grid codes.

Abstract

This application provides a path planning method, system, electronic device, and computer program product based on BeiDou grid codes. The method includes: acquiring the four-dimensional spatiotemporal space of the target path planning task and performing hierarchical division to form a four-dimensional spatiotemporal grid; generating a four-dimensional code containing longitude, latitude, altitude, and time codes for each grid based on BeiDou grid codes; generating and storing a set of spatiotemporal neighborhood codes at the current level; searching based on this set, and generating cross-level index markers using historical planning data when no matching grid is found; determining the target level based on these markers, determining the linked list insertion position through one-hot encoding bit-by-bit comparison, and establishing a cross-level mapping; continuing the search at the target level to obtain the four-dimensional spatiotemporal grid sequence and outputting the corresponding path. This method achieves spatiotemporally coupled planning and dynamic hierarchical management, improving the efficiency, accuracy, and flexibility of path planning, and is suitable for scenarios such as UAVs that require consideration of spatiotemporal constraints.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and more specifically, to a path planning method, device, medium, and program product based on BeiDou grid codes. Background Technology

[0002] In the field of path planning for intelligent devices such as drones, it is necessary to avoid both static obstacles and dynamic targets such as other drones in the buffer zone. Therefore, path planning must not only consider spatial constraints, but also incorporate time requirements to achieve spatiotemporal collaborative planning.

[0003] Current traditional path planning algorithms generally employ a spatiotemporally decoupled planning logic, first performing a spatial range search, and then conducting a time-dimensional query on the selected spatial region, failing to form a spatiotemporally integrated planning system. Furthermore, traditional algorithms do not hierarchically divide and encode the planning space, lacking a dynamic hierarchical management mechanism, and only conduct searches based on a fixed grid granularity, unable to adaptively adjust the hierarchy according to spatiotemporal density and planning accuracy requirements.

[0004] The aforementioned shortcomings lead to at least the following problems with traditional algorithms: First, the decoupling of time and space requires the planning process to handle spatial and temporal constraints separately, resulting in complex logic, high computational cost, and low planning efficiency. Second, the lack of hierarchical coding and dynamic management mechanisms leads to severe data redundancy and low memory utilization when facing large-scale planning tasks. Furthermore, the query process requires traversing a large amount of irrelevant data, and the query speed decreases significantly as the amount of planning data increases, making it difficult to meet the real-time and efficient path planning requirements of devices such as drones. Summary of the Invention

[0005] In response, this invention provides a path planning method, system, electronic device, and computer program product based on BeiDou grid codes, to at least partially solve the above-mentioned technical problems.

[0006] This invention provides a path planning method based on BeiDou grid codes, comprising the following steps:

[0007] Obtain the four-dimensional spatiotemporal space of the target path planning task, and divide the four-dimensional spatiotemporal space into a corresponding four-dimensional spatiotemporal grid by hierarchical division;

[0008] The four-dimensional spatiotemporal grid is encoded based on the BeiDou grid code, generating a four-dimensional code for each grid that is a combination of longitude code, latitude code, altitude code and time code;

[0009] A four-dimensional search is performed within the current level based on the spatiotemporal neighborhood encoding set. When there is no four-dimensional spatiotemporal grid matching the path planning conditions in the linked list structure of the current level, a cross-level index tag is generated.

[0010] Based on the cross-level index markers, the target levels to be crossed are determined, and a cross-level grid mapping is established by querying.

[0011] Continue to expand the spatiotemporal neighborhood and query the linked list index at the target level until a four-dimensional spatiotemporal grid sequence for path generation is obtained at the specified level, and output the path corresponding to the four-dimensional spatiotemporal grid sequence.

[0012] Furthermore, in the current level, based on the four-dimensional encoding of the node to be expanded, a set of spatiotemporal neighborhood encodings is generated based on a preset spatiotemporal neighborhood relationship, and the four-dimensional spatiotemporal grids corresponding to the neighborhoods are stored in a linked list structure. The linked list structure includes multiple linked list nodes arranged in order based on the BeiDou grid code, wherein each linked list node contains the four-dimensional encoding of the corresponding level and a level switching indicator field. The level switching indicator field is used to maintain the encoding continuity between different level grids in the linked list.

[0013] Furthermore, the cross-level index marker includes a multi-bit mask formed by a dimension-by-dimensional comparison based on four-dimensional encoding. The multi-bit mask is used to locate the set of nodes in the linked list that share a common prefix segment with the target level encoding.

[0014] Furthermore, the index field generated based on the combination of the multi-bit mask and the target level four-dimensional encoding is used as the insertion number of the linked list node, and a cross-level mapping node is generated in the linked list based on the insertion number.

[0015] Furthermore, the cross-level mapping node includes a level difference encoding for identifying the level span, which is used to maintain the ordered arrangement of cross-level nodes in the linked list structure.

[0016] Furthermore, the spatiotemporal neighborhood expansion at the target level includes constructing a new spatiotemporal neighborhood encoding set based on the prefix comparison results of the current four-dimensional encoding and the target level four-dimensional encoding, and traversing and querying it in the linked list structure in order of the level difference encoding.

[0017] In another aspect, this application also provides a path planning system based on BeiDou grid codes, including:

[0018] The four-dimensional spatiotemporal grid generation module is used to obtain the four-dimensional spatiotemporal space of the target path planning task and perform hierarchical division of the four-dimensional spatiotemporal space to form a corresponding four-dimensional spatiotemporal grid.

[0019] The four-dimensional encoding module is used to encode the four-dimensional spatiotemporal grid based on the Beidou grid code, and generate a four-dimensional code for each grid that is a combination of longitude code, latitude code, altitude code and time code;

[0020] The index tag generation module is used to perform a four-dimensional search within the current level based on the spatiotemporal neighborhood encoding set. When there is no four-dimensional spatiotemporal grid matching the path planning conditions in the linked list structure of the current level, cross-level index tags are generated.

[0021] The cross-level grid mapping establishment module is used to determine the target level to be crossed based on the cross-level index marker, determine the linked list insertion position based on the bitwise comparison result of the one-hot encoding of the historical planning level and the one-hot encoding of the target level, and establish the cross-level grid mapping through linked list index query.

[0022] The path output module is used to continue spatiotemporal neighborhood expansion and query at the target level until a four-dimensional spatiotemporal grid sequence for path generation is obtained at the specified level, and the path corresponding to the four-dimensional spatiotemporal grid sequence is output.

[0023] In another aspect, this application provides a computer-readable storage medium having stored thereon computer program instructions that can be executed by a processor to implement the path planning method based on BeiDou grid codes as described above.

[0024] Another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the path planning method based on BeiDou grid codes as described above.

[0025] This invention constructs a four-dimensional spatiotemporal grid encompassing longitude, latitude, altitude, and time, and performs hierarchical division. Combined with BeiDou grid codes to generate four-dimensional encoding, it achieves spatiotemporal coupled planning, effectively solving the problems of complex planning logic and high computational cost caused by spatiotemporal decoupling in traditional algorithms. By storing neighborhood grid data using a linked list structure, and employing techniques such as one-hot encoding, multi-bit masking, and hierarchical difference encoding to generate cross-level index tags and establish cross-level grid mappings, it achieves dynamic hierarchical management and efficient cross-level queries, significantly improving memory utilization and query efficiency. The query speed is significantly superior to traditional spatiotemporal separation algorithms. Furthermore, this method can adaptively adjust the hierarchy according to spatiotemporal density and planning accuracy requirements, adapting to different path planning scenarios and ensuring the accuracy and flexibility of path planning. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0027] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0028] Figure 1 This is a schematic diagram of a path planning method based on BeiDou grid codes provided in an embodiment of the present invention.

[0029] Figure 2 This is a schematic diagram of the cross-level network mapping process provided in an embodiment of the present invention.

[0030] Figure 3 This is a schematic diagram of the path output process provided in an embodiment of the present invention.

[0031] Figure 4 This is a schematic diagram of the structure of a path planning system based on BeiDou grid codes, provided in an embodiment of the present invention.

[0032] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0034] It should be noted that all user information (including but not limited to user device information, user personal information, object information corresponding to device usage data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, device usage data, etc.) involved in all embodiments of this disclosure are information and data authorized by the user or fully authorized by all parties.

[0035] The technical solutions of this application will be described in detail below with reference to various embodiments.

[0036] like Figure 1 As shown in the diagram, this invention discloses a path planning method based on BeiDou grid codes, comprising the following steps:

[0037] S1 obtains the four-dimensional spatiotemporal space of the target path planning task, and performs hierarchical division of the four-dimensional spatiotemporal space to form a corresponding four-dimensional spatiotemporal grid.

[0038] S2, based on the BeiDou grid code, the four-dimensional spatiotemporal grid is encoded to generate a four-dimensional code for each grid, which is a combination of longitude code, latitude code, altitude code and time code;

[0039] S3, In the current level, based on the four-dimensional encoding of the node to be expanded, generate its spatiotemporal neighborhood encoding set through the set spatiotemporal neighborhood relationship, and store the four-dimensional spatiotemporal grid corresponding to the neighborhood in a linked list structure.

[0040] S4. Based on the spatiotemporal neighborhood encoding set, perform a four-dimensional search within the current level. When there is no four-dimensional spatiotemporal grid matching the path planning conditions in the linked list structure of the current level, generate a cross-level index tag.

[0041] S5, determine the target level to be crossed based on the cross-level index marker, and query to establish a cross-level grid mapping;

[0042] S6. Continue to expand and query the spatiotemporal neighborhood in the target level until a four-dimensional spatiotemporal grid sequence for path generation is obtained at the specified level, and output the path corresponding to the four-dimensional spatiotemporal grid sequence.

[0043] In some embodiments, the four-dimensional spatiotemporal range of the target path planning task is first obtained. For example, in a UAV path planning scenario, the planning task can explicitly cover the constraint boundaries of the spatial and temporal dimensions, where the spatial dimension includes longitude, latitude, and altitude, and the temporal dimension is the effective execution period of the planning task.

[0044] For example, the aforementioned four-dimensional parameters can be obtained by receiving task instructions from the planning system. These instructions may include the start and end ranges of longitude and latitude, the upper and lower limits of altitude, and the time window for task execution. For instance, the longitude range could be 110°E to 112°E, the latitude range 30°N to 32°N, the altitude range 50 meters to 500 meters, and the time window could be 08:00 to 12:00 Beijing time on a specific day. After obtaining these parameters, they are standardized: the latitude and longitude data are converted to decimal format, the altitude data is standardized to a value in meters, and the time data is converted to timestamp format, ensuring the consistency and computability of the data across all dimensions.

[0045] Secondly, a pre-defined multi-level grid system is constructed. This multi-level grid system is an adaptive hierarchical structure designed based on spatiotemporal density requirements, used to adapt path planning to different levels of precision. Specifically, the hierarchical division of the multi-level grid system is based on factors including spatial extent, time span, and the precision requirements of the planning task.

[0046] For example, in planning scenarios with a wide spatial scope, long time span, and low precision requirements, a coarser-grained hierarchy can be set; conversely, in planning scenarios with a narrow spatial scope, short time span, and high precision requirements, a finer-grained hierarchy can be set. There is a clear containment relationship between the different hierarchical levels. A higher-level grid can be divided into multiple lower-level grids, and the spatial dimension corresponding to the grid side length and the time interval corresponding to the time dimension of different levels are in a fixed proportional relationship. For example, the longitude side length of a higher-level grid is twice that of a lower-level grid, and the time interval is also twice that of the lower-level grid, ensuring the regularity and consistency of the hierarchical division.

[0047] Finally, the four-dimensional space is uniformly divided according to the aforementioned multi-level grid system. Specifically, based on the standardized four-dimensional spatiotemporal range, the four dimensions of longitude, latitude, altitude, and time are divided according to the grid side length and time interval of each level in the multi-level grid system. For the longitude dimension, intervals of corresponding lengths are sequentially extracted from the starting longitude value according to the longitude side length of the current level, forming multiple longitude grid units; the division method for the latitude and altitude dimensions is the same as that for the longitude dimension, with intervals extracted according to the latitude and altitude side lengths of the corresponding levels, respectively; the time dimension is divided into time segments sequentially from the starting time value according to the time interval of the current level, forming multiple time grid units.

[0048] Through the above division, longitude, latitude, altitude, and time grid units combine to form a unique four-dimensional spatiotemporal grid. Each four-dimensional spatiotemporal grid represents a specific spatial location and a specific time segment, laying the foundation for subsequent encoding and searching. Understandably, during the division process, it is necessary to ensure that the grid units of each dimension do not overlap and fully cover the corresponding four-dimensional spatiotemporal range to avoid planning blind spots.

[0049] According to an embodiment of the present invention, a four-dimensional spatiotemporal grid is encoded based on the BeiDou grid code, and a four-dimensional code consisting of a longitude code, a latitude code, an altitude code, and a time code is generated for each grid. This four-dimensional code is used to uniquely identify the corresponding four-dimensional spatiotemporal grid.

[0050] Specifically, the BeiDou grid code, as a standardized coding system with positioning and encoding functions, essentially converts geospatial locations into binary or decimal codes using specific algorithms. In this invention, the encoding rules of the BeiDou grid code are extended to simultaneously encompass information in both the height and time dimensions, forming an encoding logic adapted to a four-dimensional spatiotemporal grid.

[0051] Specifically, the original longitude and latitude coding rules in the BeiDou grid code are retained to ensure the accuracy and compatibility of spatial location coding. For the altitude dimension, referring to the coding methods of longitude and latitude, the altitude dimension is divided into multiple continuous altitude intervals according to the altitude range and hierarchical division, and each altitude interval is assigned a unique binary code as the altitude code. For the time dimension, similarly according to the time span and hierarchical division, the time dimension is divided into multiple continuous time segments, and each time segment is assigned a unique binary code as the time code.

[0052] Next, codes for each dimension are generated. For the generation of longitude codes, the longitude grid units divided in step S1 are used as objects. According to the longitude coding rules of Beidou grid codes, the starting longitude value and ending longitude value of each longitude grid unit are input into the coding algorithm to calculate the binary longitude code corresponding to the longitude grid unit.

[0053] For example, if the longitude range of a certain longitude grid unit is 110.5° to 110.6° east longitude, after conversion using the BeiDou grid code encoding algorithm, the corresponding 6-bit binary longitude code is obtained as 010110. The generation method of the latitude code is the same as that of the longitude code. Taking the latitude range of the latitude grid unit as input, the corresponding binary latitude code is generated through the BeiDou grid code latitude encoding algorithm. For example, if the latitude range of a certain latitude grid unit is 30.2° to 30.3° north latitude, the generated 6-bit binary latitude code is 101001.

[0054] The altitude code is generated based on the altitude grid cells divided in step S1. According to the preset altitude encoding rules, the altitude range of the altitude grid cells is converted into binary code. For example, for an altitude grid cell with an altitude range of 100 meters to 150 meters, the generated 4-bit binary altitude code is 0011. The time code is generated based on the time grid cells divided in step S1. According to the preset time encoding rules, the time segment of the time grid cell is converted into binary code. For example, for a time grid cell with a time segment of 09:00 to 09:30, the generated 4-bit binary time code is 1001.

[0055] Finally, a four-dimensional code is generated. Specifically, the generated longitude, latitude, altitude, and time codes are concatenated in a fixed order to form a four-dimensional code that uniquely identifies a four-dimensional spatiotemporal grid. Preferably, the concatenation order is longitude code first, latitude code second, altitude code third, and time code last, ensuring the uniformity and readability of the code. For example, if the longitude code corresponding to a certain four-dimensional spatiotemporal grid is 010110, the latitude code is 101001, the altitude code is 0011, and the time code is 1001, then the concatenated four-dimensional code is 01011010100100111001. It can be understood that since the code of each dimension is a unique identifier for the corresponding grid unit, the combined four-dimensional code can uniquely correspond to a four-dimensional spatiotemporal grid, and there will be no code duplication.

[0056] According to an embodiment of the present invention, in the current level, based on the four-dimensional encoding of the node to be expanded, a set of its spatiotemporal neighborhood encodings is generated through the set spatiotemporal neighborhood relationships, and the four-dimensional spatiotemporal grid corresponding to the neighborhood is stored in a linked list structure.

[0057] Specifically, first, the nodes to be expanded and their four-dimensional codes are determined. In the path planning process, nodes to be expanded refer to nodes whose surrounding spatiotemporal range needs further exploration during the current path search. The four-dimensional code corresponding to this node is the code of a certain four-dimensional spatiotemporal grid generated in step S2. For example, if the current path planning has searched to a four-dimensional spatiotemporal grid with the code 01011010100100111001, then the node corresponding to this grid is the node to be expanded, and its four-dimensional code is the aforementioned code.

[0058] Secondly, the spatiotemporal neighborhood relationships are defined. Spatiotemporal neighborhood relationships refer to the relational conditions satisfied by the spatiotemporal grids adjacent to the four-dimensional spatiotemporal grid corresponding to the node to be expanded in the current level of the four-dimensional spatiotemporal grid, including spatial neighborhood relationships and temporal neighborhood relationships.

[0059] Specifically, spatial neighborhood relationships refer to the neighborhood definition in traditional spatial planning, combined with the spatial dimensional division of a four-dimensional spatiotemporal grid. The spatial neighborhood of a given four-dimensional spatiotemporal grid is defined as the grids adjacent to it in the three dimensions of longitude, latitude, and altitude, including adjacent grids in the front-back, left-right, and up-down directions, ensuring spatial continuity. Temporal neighborhood relationships are defined as the grids corresponding to time segments adjacent to the time segments of the four-dimensional spatiotemporal grid, including grids corresponding to the preceding and following time segments, ensuring temporal continuity. Through the combination of these spatial and temporal neighborhood relationships, a complete spatiotemporal neighborhood relationship is formed. For example, the spatiotemporal neighborhood of a given four-dimensional spatiotemporal grid includes 26 spatially adjacent grids and 2 temporally adjacent grids, totaling 28 neighborhood grids. The specific number can be adjusted according to actual planning needs; this invention does not impose any limitations.

[0060] Then, a spatiotemporal neighborhood code set is generated. Specifically, based on the four-dimensional code of the node to be expanded, the longitude code, latitude code, altitude code, and time code in the four-dimensional code are adjusted according to the set spatiotemporal neighborhood relationship to obtain the four-dimensional code corresponding to each neighborhood grid.

[0061] For example, regarding the adjustment of longitude codes, if the longitude code of the node to be expanded is 010110, which corresponds to a certain longitude interval, then the longitude codes of the adjacent grids in the longitude direction are 010101, which corresponds to the previous longitude interval, and 010111, which corresponds to the next longitude interval. The adjustment method for latitude and altitude codes is the same as that for longitude codes, and the encoding is adjusted according to the position of the latitude and altitude neighborhoods, respectively. The adjustment of time codes involves converting the time code of the node to be expanded into the encoding corresponding to the previous time segment and the encoding corresponding to the next time segment. For example, if the time code of the node to be expanded is 1001, which corresponds to 09:00 to 09:30, then the time code of the time neighborhood is 1000, which corresponds to 08:30 to 09:00, and 1010 corresponds to 09:30 to 10:00. The codes adjusted in each dimension are combined according to the splicing order set in step S2 to obtain the four-dimensional code corresponding to each neighborhood grid. The four-dimensional codes of all neighborhood grids together constitute the spatiotemporal neighborhood code set.

[0062] Optionally, the linked list structure used in step S3 includes multiple linked list nodes arranged according to the BeiDou grid code order. Each linked list node contains a four-dimensional code of the corresponding level and a level switching indicator field. The level switching indicator field is used to maintain the coding continuity between different grid levels in the linked list.

[0063] Specifically, the construction process of the linked list structure is as follows: First, the storage structure of the linked list nodes is determined. In addition to storing the four-dimensional code of the corresponding four-dimensional spatiotemporal grid, each linked list node also sets a level switching indicator field. This field is a binary flag bit used to indicate whether the current node has cross-level related nodes. For example, when the level switching indicator field is 1, it means that the node has a corresponding cross-level node; when the field is 0, it means that the node only has related nodes in the current level.

[0064] Secondly, the linked list nodes are arranged according to the order of the BeiDou grid codes, based on the lexicographical order of the four-dimensional codes, ensuring the ordered nature of the linked list nodes and facilitating subsequent traversal and querying. When storing the four-dimensional spatiotemporal grids corresponding to the spatiotemporal neighborhood code set, the four-dimensional code of each neighborhood grid is stored in its corresponding linked list node. A corresponding level switching indicator field value is set based on whether the neighborhood grid has cross-level related nodes. These linked list nodes are then inserted into the linked list structure in lexicographical order to complete the storage of the spatiotemporal neighborhood code set. This linked list structure design allows for the storage of the current level neighborhood grid data while providing a basis for subsequent cross-level queries, ensuring the continuity of the codes and the efficiency of the queries.

[0065] According to an embodiment of the present invention, a four-dimensional search is performed within the current level based on the spatiotemporal neighborhood encoding set. When there is no four-dimensional spatiotemporal grid matching the path planning conditions in the linked list structure of the current level, a cross-level index tag is generated based on the hierarchical records of historical planning data and the corresponding one-hot encoding.

[0066] Specifically, path planning conditions refer to the constraints imposed by the path planning task on the four-dimensional spatiotemporal grid, including spatial and temporal constraints. For example, spatial constraints include avoiding grids containing static obstacles and buffering grids occupied by drones, while temporal constraints require the path to pass through a grid within the task execution time window and without other drones occupying it. These constraints are pre-set by the planning system according to task requirements and converted into a standard format that can be compared with the attributes of the four-dimensional spatiotemporal grid.

[0067] Next, a four-dimensional search is performed within the current level. Specifically, the linked list structure constructed in step S3 is traversed, and the four-dimensional code stored in each linked list node is read sequentially. Based on the four-dimensional code, the longitude range, latitude range, altitude range, and time segment of the corresponding four-dimensional spatiotemporal grid are parsed out. The parsed grid attributes are compared one by one with the path planning conditions to determine whether the four-dimensional spatiotemporal grid meets all the constraints.

[0068] For example, if the spatial range of a four-dimensional spatiotemporal grid does not overlap with the range of static obstacles, no other drones occupy it during the time segment, and its height meets the planning requirements, then the grid is determined to match the path planning conditions; otherwise, it is determined to be a mismatch. During the traversal, if at least one four-dimensional spatiotemporal grid that matches the path planning conditions is found, the search at the current level is stopped, and the grid is used as a candidate node for path expansion; if no four-dimensional spatiotemporal grid that matches the path planning conditions is found after traversing the entire linked list structure, then the current level is determined to be unable to meet the path planning requirements, and the cross-level index tag generation process needs to be initiated.

[0069] Next, the hierarchical records of historical planning data and their corresponding one-hot codes are obtained. The hierarchical records of historical planning data refer to the grid usage records of each level involved in past path planning tasks, including information such as the grid code, usage time, and planning results for each level. These records are stored in a dedicated database for easy querying and retrieval.

[0070] One-hot encoding is a method of encoding hierarchical information in historical planning data. Each level corresponds to a unique one-hot code, which is a binary string where only the bit corresponding to the level is 1, and the rest are 0. For example, the one-hot code for level k is 0010000000000, where only the k-th bit is 1. One-hot encoding can quickly identify the level to which historical planning data belongs. When cross-level index tags need to be generated, the hierarchical records of historical planning data related to the current planning task are queried from the database. All levels involved are filtered out, and the one-hot code corresponding to each level is obtained, forming a mapping table between historical planning levels and one-hot codes.

[0071] Understandably, in the absence of historical planning data, initial cross-level index markers can be generated directly based on a pre-defined multi-level grid system and the four-dimensional coding features of the current level. Specifically, the initial one-hot coding corresponding to each level is pre-defined, that is, a unique identifier is assigned according to the level priority. The four-dimensional coding of the current level is compared with the four-dimensional coding of each candidate target level in a dimension-by-dimensional prefix comparison, common prefix segments are extracted and multi-bit masks are generated. These multi-bit masks are associated with the initial one-hot coding of the candidate target level to form the initial cross-level index markers.

[0072] Optionally, the cross-level index marker generated in step S4 includes a multi-bit mask formed by the dimension-by-dimensional comparison result based on the four-dimensional encoding. The multi-bit mask is used to locate the set of nodes in the linked list that have a common prefix segment with the target level encoding.

[0073] Specifically, the generation process of cross-level index tags is as follows: First, the four-dimensional code of the current level is compared dimension by dimension with the four-dimensional codes of each level in the historical planning data. The comparison dimensions include longitude code, latitude code, altitude code, and time code. During the comparison process, the common prefix parts in each dimension code are extracted and used as common prefix segments. For example, if the longitude code of a certain four-dimensional code in the current level is 010110, and the longitude code of the corresponding four-dimensional code in the historical planning data is 010100, the common prefix segment of the two is 0101; the extraction method of the common prefix segments of latitude code, altitude code, and time code is the same as that of longitude code.

[0074] Secondly, a multi-bit mask is generated based on the common prefix segments obtained from the dimension-by-dimensional alignment. The multi-bit mask is a binary string with the same length as the four-dimensional code. Bits corresponding to the common prefix segments are set to 1, and the remaining bits are set to 0. For example, if the four-dimensional code is 20 bits long and the common prefix segment obtained after dimension-by-dimensional alignment is 12 bits long, then the first 12 bits of the multi-bit mask are 1, and the last 8 bits are 0. This multi-bit mask can identify the node features that share common prefix segments with the target level code. Using this mask, the set of nodes matching this feature can be quickly located in the linked list, providing accurate indexing for subsequent cross-level queries. After generating the multi-bit mask, it is associated with the hierarchical records and one-hot codes of historical planning data to form a cross-level index marker. This marker contains the hierarchical association information and node location information required for cross-level queries, ensuring the targeting and efficiency of cross-level queries.

[0075] According to an embodiment of the present invention, the target level to be traversed is determined based on the cross-level index marker, and the linked list insertion position is determined by the bitwise comparison result of the historical planning one-hot encoding and the target level one-hot encoding. A cross-level mesh mapping is then established using the corresponding linked list. Please refer to... Figure 2 , Figure 2 This is a schematic diagram of the cross-level network mapping process provided in an embodiment of the present invention.

[0076] Specifically, in S201, the target levels to be traversed are determined. Specifically, the cross-level index markers generated in step S4 are parsed, and the corresponding relationship table between the level records and one-hot codes of the historical planning data contained therein is extracted. Based on the accuracy requirements and spatiotemporal density of the current planning task, levels that may meet the path planning conditions are selected from this relationship table as candidate target levels.

[0077] For example, if the current level is a coarse-grained level and no matching grid is found, a level with finer grained ...

[0078] Secondly, in S202, the historical planning one-hot code and the target level one-hot code are obtained. The historical planning one-hot code refers to the one-hot code corresponding to the level of the historical planning data related to the current planning task obtained in step S4, and the target level one-hot code refers to the one-hot code corresponding to the target level determined in step S5. Both are in binary string format and have the same length. For example, the historical planning one-hot code is 0010001001000, and the target level one-hot code is 0000000011111.

[0079] Then, in S203, a bitwise comparison is performed between the historical planning one-hot code and the target level one-hot code. Specifically, a bitwise AND operation is used to calculate the two one-hot codes. The rule for the bitwise AND operation is: for corresponding bits of the two codes, if both are 1, the result is 1; otherwise, it is 0. Through this operation, the common bit information of the two codes can be obtained, that is, the feature bits that belong to both the historical planning level and the target level. For example, if the historical planning one-hot code is 0010001001000 and the target level one-hot code is 0000000011111, the bitwise AND operation result of the two is 0000000001000.

[0080] Optionally, determining the insertion position of the linked list in step S5 includes using an index field generated by combining a multi-bit mask with the four-dimensional encoding of the target level as the insertion number of the linked list node, and generating a cross-level mapping node in the linked list based on the insertion number.

[0081] Specifically, firstly, the multi-bit mask generated in step S4 and the four-dimensional code of the target level are obtained, and then a bitwise AND operation is performed on the two to obtain the combined encoding result, which is the index field.

[0082] Specifically, it is ensured that the multi-bit mask and the target level four-dimensional code are binary strings of equal length. If the lengths are inconsistent, the shorter one is padded with 0s in the high bits to make them the same length. The multi-bit mask is a binary string generated by comparing the four-dimensional codes of the current level and the candidate target level one by one. The common prefix segment corresponds to 1, and the remaining bits are 0. The target level four-dimensional code is the complete four-dimensional code of the grid to be mapped in the target level.

[0083] A bitwise logical AND operation is performed on a two-bit binary string of equal length. This bitwise AND operation allows for the precise extraction of code segments from the target-level four-dimensional encoding that share commonalities with the current level, while filtering out irrelevant, differentiated code segments. The operation rule is: for the i-th bit, if both the i-th bit of the mask and the i-th bit of the target-level four-dimensional encoding are 1, the result bit is 1; otherwise, it is 0. The formula is:

[0084] in, For index fields, For multi-bit masks, Four-dimensional encoding for the target level. This indicates a bitwise AND operation.

[0085] The binary index field obtained from the operation is converted into a decimal integer, which is the insertion number of the linked list node. For example, if the multi-bit mask is 01111100000000 (14 bits) and the target level four-dimensional code is 01011010100100 (14 bits), the bitwise AND operation result is 01011000000000, which, after conversion to decimal, yields the insertion number 22.

[0086] When generating cross-level mapping nodes, the four-dimensional encoding of the four-dimensional spatiotemporal grid that satisfies the path planning conditions in the target level is stored in the node, and the corresponding level switching indicator field value is set. Then, the cross-level mapping node is inserted into the linked list structure according to the insertion sequence number, ensuring the order of the linked list. In this way, the insertion position of the linked list can be accurately determined, achieving ordered storage of cross-level nodes.

[0087] After the index field is converted into an insertion number, the earlier the common prefix segment appears, the higher the spatiotemporal granularity. The smaller the insertion number, the earlier the node appears in the linked list. Conversely, the later the common prefix segment appears, the finer the spatiotemporal feature. The larger the insertion number, the later the node appears in the linked list. Therefore, when traversing the linked list, searches can be performed sequentially from coarse to fine spatiotemporal granularity.

[0088] Furthermore, the cross-level mapping node includes a level difference encoding for identifying the level span, which is used to maintain the ordered arrangement of cross-level nodes in the linked list structure.

[0089] Specifically, the level difference encoding is a binary code generated based on the level difference between the current level and the target level. For example, if the current level is k and the target level is k+2, the level difference is 2, and the corresponding level difference encoding is 0010. When generating cross-level mapping nodes, this level difference encoding is stored in a specific field of the node. When multiple cross-level mapping nodes are inserted into the linked list, they are sorted according to the lexicographical order of the level difference encoding, ensuring that cross-level nodes are arranged in an orderly manner in the linked list. This design enables the rapid identification of the level span of nodes based on the level difference encoding during subsequent linked list traversal, improving the efficiency of cross-level queries while maintaining the orderliness and integrity of the linked list structure.

[0090] Finally, in S204, a cross-level grid mapping is established using corresponding linked lists. Specifically, after inserting the cross-level mapping node into the linked list structure, this node establishes an association with the linked list nodes of the current level through a level switching indicator field and a level difference code. For example, if the level switching indicator field of a linked list node in the current level is 1, and its four-dimensional code shares a common prefix with the four-dimensional code of the cross-level mapping node, then this current level node and the cross-level mapping node form a mapping relationship, indicating that this node in the current level can be traversed to the corresponding node in the target level. Through the establishment of this mapping relationship, the association between the grid data of the current level and the target level is realized, providing path guidance for subsequent searches in the target level.

[0091] According to an embodiment of the present invention, please refer to Figure 3 , Figure 3 This is a schematic diagram of the path output process provided in an embodiment of the present invention. In the target level, the spatiotemporal neighborhood expansion and linked list index query are continued until a four-dimensional spatiotemporal grid sequence for path generation is obtained at the specified level, and the path corresponding to the sequence is output.

[0092] Specifically, firstly, in S301, switch to the target level. Based on the target level determined in step S5, adjust the hierarchical context of the path planning, switch the current search level from the original level to the target level, and load the multi-level grid system, four-dimensional encoding rules, and linked list structure corresponding to the target level, including the historically stored target level grid data and the cross-level mapping nodes inserted in step S5.

[0093] Secondly, in S302, spatiotemporal neighborhood expansion is performed at the target level. Specifically, based on the four-dimensional encoding corresponding to the cross-level mapping node established in step S5, and referring to the spatiotemporal neighborhood relationship set set in step S3, a spatiotemporal neighborhood encoding set for that node in the target level is generated. During the expansion process, the parameters of the spatiotemporal neighborhood relationship need to be adjusted according to the grid granularity of the target level. For example, when the target level is a finer-grained level, the number of grids in the spatial neighborhood may increase, and the time interval of the temporal neighborhood may be shortened to ensure the adaptability of the neighborhood expansion.

[0094] Optionally, the spatiotemporal neighborhood expansion at the target level in step S6 includes constructing a new spatiotemporal neighborhood encoding set based on the prefix comparison results of the current four-dimensional encoding and the target level four-dimensional encoding, and traversing and querying it in the linked list structure in order of the hierarchical difference encoding.

[0095] Specifically, firstly, a prefix comparison is performed between the four-dimensional encoding of the current cross-level mapping node and the four-dimensional encoding of the target level to extract their common prefix segments, ensuring the relevance of the neighborhood expansion. Then, based on the spatiotemporal neighborhood relationship between this common prefix segment and the target level, the encodings of each dimension are adjusted to generate a new set of spatiotemporal neighborhood encodings. All encodings in this set belong to the target level and have a spatiotemporal neighborhood relationship with the current node. During linked list index queries, the linked list structure of the target level is traversed in lexicographical order according to the level difference encoding, comparing the four-dimensional encodings of the linked list nodes with the path planning conditions sequentially, improving the targeting and efficiency of the query. In this way, matching grid nodes can be quickly located in the target level, shortening the search time.

[0096] Then, in S303, a linked list index query is performed at the target level. The linked list structure of the target level is traversed, and the attributes of the four-dimensional spatiotemporal grids corresponding to the four-dimensional codes in the linked list nodes are compared according to the path planning conditions set in step S4. If a four-dimensional spatiotemporal grid matching the path planning conditions is found, this grid is used as a candidate node in the target level, and the spatiotemporal neighborhood expansion and linked list index query process is repeated based on this node to continue expanding the path in the target level. If no matching grid is found, the existence of other traversable target levels is determined based on the hierarchical records of historical planning data. If so, steps S4 to S5 are returned, a new cross-level index marker is generated, a new cross-level grid mapping is established, and the search is switched to the new target level. If no other traversable target levels exist, the path planning is deemed to have failed, and a failure message is returned to the planning system.

[0097] During the search process described above, the four-dimensional codes of the four-dimensional spatiotemporal grids that satisfy the path planning conditions are continuously recorded, forming a four-dimensional spatiotemporal grid sequence according to the path expansion order. Each grid in this sequence satisfies the path planning conditions, and adjacent grids have spatiotemporal neighborhood relationships, ensuring the continuity and feasibility of the path. When the searched four-dimensional spatiotemporal grid sequence reaches the endpoint conditions required by the path planning task, such as the endpoint position and endpoint time corresponding to the last grid of the sequence, the search stops, and this four-dimensional spatiotemporal grid sequence is determined as the final planning result.

[0098] Finally, in S304, the path corresponding to the four-dimensional spatiotemporal grid sequence is output. Specifically, the four-dimensional code of each grid in the four-dimensional spatiotemporal grid sequence is parsed to extract the corresponding longitude range, latitude range, altitude range, and time segment. The center coordinates of each grid are calculated, including the center values ​​of longitude, latitude, and altitude, and the center time. These center coordinates and center times are concatenated in sequence to form a continuous path point sequence, where each path point contains longitude, latitude, altitude, and time information. This path point sequence is converted into a path format supported by the planning system, such as JSON or XML, and output to the planning system. The system then controls the UAV's flight trajectory based on this path point sequence to complete the path planning task.

[0099] In summary, the path planning algorithm based on BeiDou grid codes described in this invention achieves efficient path planning with spatiotemporal coupling through a series of steps, including constructing a four-dimensional spatiotemporal grid, generating four-dimensional codes, storing neighborhood data in linked lists, hierarchical search, and cross-level mapping. The design of the multi-level grid system and four-dimensional coding solves the problem of spatiotemporal decoupling in traditional algorithms, while the design of the linked list structure and cross-level index tags achieves efficient memory utilization and improved query efficiency. The close correlation and collaborative work among the steps ensure the accuracy and efficiency of path planning, making it particularly suitable for path planning scenarios such as those involving UAVs that require consideration of spatiotemporal constraints.

[0100] Please see Figure 4 , Figure 4 A path planning system 400 based on BeiDou grid codes is shown. The system implementation is similar to... Figure 1 Corresponding to the method embodiments shown, this system can be specifically applied to various electronic devices, specifically including,

[0101] The four-dimensional spatiotemporal grid generation module 401 is used to obtain the four-dimensional spatiotemporal space of the target path planning task and perform hierarchical division of the four-dimensional spatiotemporal space to form a corresponding four-dimensional spatiotemporal grid.

[0102] The four-dimensional encoding module 402 is used to encode the four-dimensional spatiotemporal grid based on the Beidou grid code, and generate a four-dimensional code for each grid that is a combination of longitude code, latitude code, altitude code and time code.

[0103] The index tag generation module 403 is used to perform a four-dimensional search within the current level based on the spatiotemporal neighborhood encoding set. When there is no four-dimensional spatiotemporal grid matching the path planning conditions in the linked list structure of the current level, cross-level index tags are generated.

[0104] The cross-level grid mapping establishment module 404 is used to determine the target level to be crossed based on the cross-level index marker, and query and establish the cross-level grid mapping;

[0105] The path output module 405 is used to continue spatiotemporal neighborhood expansion and query at the target level until a four-dimensional spatiotemporal grid sequence for path generation is obtained at the specified level, and the path corresponding to the four-dimensional spatiotemporal grid sequence is output.

[0106] Based on the same inventive concept, this application also provides an electronic device. The method corresponding to the electronic device can be the method in the foregoing embodiments, and its problem-solving principle is similar to that method. The electronic device provided in this application includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the methods and / or technical solutions of the foregoing embodiments of this application.

[0107] The electronic device can be a user device, or a device formed by integrating user devices and network devices through a network, or it can be an application running on the aforementioned devices. The user device includes, but is not limited to, various terminal devices such as computers, mobile phones, tablets, smartwatches, and smart bands. The network device includes, but is not limited to, network hosts, single network servers, multiple network server sets, or cloud computing-based computer sets, and can be used to implement some processing functions when setting an alarm clock. Here, the cloud consists of a large number of hosts or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a virtual computer composed of a group of loosely coupled computer sets.

[0108] Figure 5 The diagram illustrates the structure of an apparatus suitable for implementing the methods and / or technical solutions in the embodiments of this application. The apparatus 500 includes a central processing unit 501. It is understood that the processing unit may also be a GPU, and this invention is not limited thereto. It can perform various appropriate actions and processes based on a program stored in read-only memory 502 or a program loaded from storage portion 508 into random access memory 503. Various programs and data required for system operation are also stored in RAM 503. The CPU 501, ROM 502, and RAM 503 are interconnected via bus 504. An input / output interface 505 is also connected to bus 504.

[0109] The following components are connected to I / O interface 505: input section 506 including keyboard, mouse, touch screen, microphone, infrared sensor, etc.; output section 507 including cathode ray tube, liquid crystal display, LED display, OLED display, etc., and speaker, etc.; storage section 508 including one or more computer-readable media such as hard disk, optical disk, magnetic disk, semiconductor memory, etc.; and communication section 509 including network interface card such as LAN card, modem, etc. Communication section 509 performs communication processing via a network such as the Internet.

[0110] In particular, the methods and / or embodiments in this application can be implemented as computer software programs. For example, the embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. When the computer program is executed by the central processing unit (CPU) 501, it performs the functions defined in the methods of this application.

[0111] Another embodiment of this application provides a computer-readable storage medium having computer program instructions stored thereon, which can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of this application described above.

[0112] Specifically, this embodiment may employ any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0113] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0114] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0115] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0116] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0117] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or page components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0121] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0123] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a device claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

Claims

1. A path planning method based on BeiDou grid codes, characterized in that, Includes the following steps, Obtain the four-dimensional spatiotemporal space of the target path planning task, and divide the four-dimensional spatiotemporal space into a corresponding four-dimensional spatiotemporal grid by hierarchical division; The four-dimensional spatiotemporal grid is encoded based on the BeiDou grid code, generating a four-dimensional code for each grid that is a combination of longitude code, latitude code, altitude code and time code; A four-dimensional search is performed within the current level based on the spatiotemporal neighborhood encoding set. When there is no four-dimensional spatiotemporal grid matching the path planning conditions in the linked list structure of the current level, a cross-level index tag is generated. Based on the cross-level index markers, the target levels to be crossed are determined, and a cross-level grid mapping is established by querying. Continue to expand and query the spatiotemporal neighborhood at the target level until a four-dimensional spatiotemporal grid sequence for path generation is obtained at the specified level, and output the path corresponding to the four-dimensional spatiotemporal grid sequence.

2. The path planning method based on BeiDou grid codes according to claim 1, characterized in that, in, In the current level, based on the four-dimensional encoding of the node to be expanded, a set of spatiotemporal neighborhood encodings is generated based on the preset spatiotemporal neighborhood relationship, and the four-dimensional spatiotemporal grids corresponding to the neighborhoods are stored in a linked list structure. The linked list structure includes multiple linked list nodes arranged in order based on the Beidou grid code. Each linked list node contains the four-dimensional encoding of the corresponding level and a level switching indicator field. The level switching indicator field is used to maintain the encoding continuity between different level grids in the linked list.

3. The path planning method based on BeiDou grid codes according to claim 2, characterized in that, The cross-level index marker includes a multi-bit mask formed by the dimension-by-dimensional comparison result based on the four-dimensional encoding. The multi-bit mask is used to locate the set of nodes in the linked list that have a common prefix segment with the target level encoding.

4. The path planning method based on BeiDou grid codes according to claim 3, characterized in that, The index field generated by the combination of the multi-bit mask and the target level four-dimensional encoding is used as the insertion number of the linked list node, and a cross-level mapping node is generated in the linked list based on the insertion number.

5. The path planning method based on BeiDou grid codes according to claim 4, characterized in that, The cross-level mapping node contains a level difference code for identifying the level span, which is used to maintain the ordered arrangement of cross-level nodes in the linked list structure.

6. The path planning method based on BeiDou grid codes according to claim 5, characterized in that, Further spatiotemporal neighborhood expansion at the target level includes constructing a new spatiotemporal neighborhood encoding set based on the prefix comparison results between the current four-dimensional encoding and the target level four-dimensional encoding, and traversing and querying it in the linked list structure in order of the level difference encoding.

7. A path planning system based on BeiDou grid codes, characterized in that, include: The four-dimensional spatiotemporal grid generation module is used to obtain the four-dimensional spatiotemporal space of the target path planning task and perform hierarchical division of the four-dimensional spatiotemporal space to form a corresponding four-dimensional spatiotemporal grid. The four-dimensional encoding module is used to encode the four-dimensional spatiotemporal grid based on the Beidou grid code, and generate a four-dimensional code for each grid that is a combination of longitude code, latitude code, altitude code and time code; The index tag generation module is used to perform a four-dimensional search within the current level based on the spatiotemporal neighborhood encoding set. When there is no four-dimensional spatiotemporal grid matching the path planning conditions in the linked list structure of the current level, cross-level index tags are generated. The cross-level grid mapping establishment module is used to determine the target level to be crossed based on the cross-level index marker, and to query and establish the cross-level grid mapping; The path output module is used to continue spatiotemporal neighborhood expansion and query at the target level until a four-dimensional spatiotemporal grid sequence for path generation is obtained at the specified level, and the path corresponding to the four-dimensional spatiotemporal grid sequence is output.

8. An electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A computer-readable medium having stored thereon computer program instructions that can be executed by a processor to implement the method as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method as described in any one of claims 1-6.

Images